Triple

T14700935
Position Surface form Disambiguated ID Type / Status
Subject James Hugh Calum Laurie E345292 entity
Predicate spouse P13 FINISHED
Object Jo Green E345295 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Jo Green | Statement: [James Hugh Calum Laurie, spouse, Jo Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jo Green
Context triple: [James Hugh Calum Laurie, spouse, Jo Green]
  • A. Jo Green chosen
    Jo Green is a British theatre administrator best known as the longtime wife of actor and comedian Hugh Laurie.
  • B. Jo Green
    Jo Green is a fictional character played by actress Mackenzie Foy, best known from her role in the film "The Nutcracker and the Four Realms."
  • C. Bammie Green
    Bammie Green was the husband of American actress Anne Francis, known primarily in connection with her personal life rather than for a public career of his own.
  • D. Joan Templeman
    Joan Templeman is the longtime partner and wife of British entrepreneur Sir Richard Branson, known for her low public profile despite her association with the Virgin Group founder.
  • E. Karen Morley
    Karen Morley was an American film actress of the 1930s, best known for her roles in pre-Code Hollywood crime dramas and social-themed films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d822e4a8c08190a155df736bb7bc13 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb605f5948190ab6b20887c4b6833 completed April 14, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf0841da48190991d5045954a32ab completed May 8, 2026, 2:17 p.m.
Created at: April 10, 2026, 1:28 a.m.